mirror of
https://github.com/hwchase17/langchain.git
synced 2025-06-24 23:54:14 +00:00
docs: add page for Firestore Chat Message History integration (#15554)
- **Description:** Adds documentation for the `FirestoreChatMessageHistory` integration and lists integration in Google's documentation - **Issue:** NA - **Dependencies:** No --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
This commit is contained in:
Averi Kitsch
GitHub
parent
ddf4e7c633
commit
ee378a0f40
@ -0,0 +1,147 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "91c6a7ef",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Google Cloud Firestore\n",
|
||||
"\n",
|
||||
"> [`Cloud Firestore`](https://cloud.google.com/firestore) is a NoSQL document database built for automatic scaling, high performance, and ease of application development.\n",
|
||||
"\n",
|
||||
"This notebook goes over how to use Firestore to store chat message history."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "2d6ed3c8-b70a-498c-bc9e-41b91797d3b7",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Setting up"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "b8eca282",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"To run this notebook, you will need a Google Cloud Project, a Firestore database instance in Native Mode, and Google credentials, see [Firestore Quickstarts](https://cloud.google.com/firestore/docs/quickstarts)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "5a7f3b3f-d9b8-4577-a7ef-bdd8ecaedb70",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"!pip install firebase-admin"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "a8e63850-3e14-46fe-a59e-be6d6bf8fe61",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Basic Usage"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "d15e3302",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain_community.chat_message_histories.firestore import (\n",
|
||||
" FirestoreChatMessageHistory,\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"message_history = FirestoreChatMessageHistory(\n",
|
||||
" collection_name=\"langchain-chat-history\",\n",
|
||||
" session_id=\"user-session-id\",\n",
|
||||
" user_id=\"user-id\",\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"message_history.add_user_message(\"hi!\")\n",
|
||||
"message_history.add_ai_message(\"whats up?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "64fc465e",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[HumanMessage(content='hi!'),\n",
|
||||
" HumanMessage(content='hi!'),\n",
|
||||
" AIMessage(content='whats up?')]"
|
||||
]
|
||||
},
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"message_history.messages"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "4be8576e",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Custom Firestore Client"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "12999273",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import firebase_admin\n",
|
||||
"from firebase_admin import credentials, firestore\n",
|
||||
"\n",
|
||||
"# Use a service account.\n",
|
||||
"cred = credentials.Certificate(\"path/to/serviceAccount.json\")\n",
|
||||
"\n",
|
||||
"app = firebase_admin.initialize_app(cred)\n",
|
||||
"client = firestore.client(app=app)\n",
|
||||
"\n",
|
||||
"message_history = FirestoreChatMessageHistory(\n",
|
||||
" collection_name=\"langchain-chat-history\",\n",
|
||||
" session_id=\"user-session-id\",\n",
|
||||
" user_id=\"user-id\",\n",
|
||||
" firestore_client=client,\n",
|
||||
")"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.11.5"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@ -186,7 +186,7 @@ from langchain_community.document_loaders import GoogleSpeechToTextLoader
|
||||
### Google Vertex AI Vector Search
|
||||
|
||||
> [Google Vertex AI Vector Search](https://cloud.google.com/vertex-ai/docs/matching-engine/overview),
|
||||
> formerly known as `Vertex AI Matching Engine`, provides the industry's leading high-scale
|
||||
> formerly known as `Vertex AI Matching Engine`, provides the industry's leading high-scale
|
||||
> low latency vector database. These vector databases are commonly
|
||||
> referred to as vector similarity-matching or an approximate nearest neighbor (ANN) service.
|
||||
|
||||
@ -207,7 +207,7 @@ from langchain_community.vectorstores import MatchingEngine
|
||||
> [Google BigQuery](https://cloud.google.com/bigquery),
|
||||
> BigQuery is a serverless and cost-effective enterprise data warehouse in Google Cloud.
|
||||
>
|
||||
> Google BigQuery Vector Search
|
||||
> Google BigQuery Vector Search
|
||||
> BigQuery vector search lets you use GoogleSQL to do semantic search, using vector indexes for fast but approximate results, or using brute force for exact results.
|
||||
|
||||
> It can calculate Euclidean or Cosine distance. With LangChain, we default to use Euclidean distance.
|
||||
@ -228,7 +228,7 @@ from langchain.vectorstores import BigQueryVectorSearch
|
||||
|
||||
>[Google ScaNN](https://github.com/google-research/google-research/tree/master/scann)
|
||||
> (Scalable Nearest Neighbors) is a python package.
|
||||
>
|
||||
>
|
||||
>`ScaNN` is a method for efficient vector similarity search at scale.
|
||||
|
||||
>`ScaNN` includes search space pruning and quantization for Maximum Inner
|
||||
@ -285,9 +285,9 @@ from langchain.retrievers import GoogleVertexAISearchRetriever
|
||||
|
||||
### Document AI Warehouse
|
||||
> [Google Cloud Document AI Warehouse](https://cloud.google.com/document-ai-warehouse)
|
||||
> allows enterprises to search, store, govern, and manage documents and their AI-extracted
|
||||
> allows enterprises to search, store, govern, and manage documents and their AI-extracted
|
||||
> data and metadata in a single platform.
|
||||
>
|
||||
>
|
||||
|
||||
```python
|
||||
from langchain.retrievers import GoogleDocumentAIWarehouseRetriever
|
||||
@ -304,9 +304,9 @@ documents = docai_wh_retriever.get_relevant_documents(
|
||||
|
||||
### Google Cloud Text-to-Speech
|
||||
|
||||
>[Google Cloud Text-to-Speech](https://cloud.google.com/text-to-speech) enables developers to
|
||||
> synthesize natural-sounding speech with 100+ voices, available in multiple languages and variants.
|
||||
> It applies DeepMind’s groundbreaking research in WaveNet and Google’s powerful neural networks
|
||||
>[Google Cloud Text-to-Speech](https://cloud.google.com/text-to-speech) enables developers to
|
||||
> synthesize natural-sounding speech with 100+ voices, available in multiple languages and variants.
|
||||
> It applies DeepMind’s groundbreaking research in WaveNet and Google’s powerful neural networks
|
||||
> to deliver the highest fidelity possible.
|
||||
|
||||
We need to install a python package.
|
||||
@ -354,7 +354,7 @@ from langchain.tools import GooglePlacesTool
|
||||
### Google Search
|
||||
|
||||
- Set up a Custom Search Engine, following [these instructions](https://stackoverflow.com/questions/37083058/programmatically-searching-google-in-python-using-custom-search)
|
||||
- Get an API Key and Custom Search Engine ID from the previous step, and set them as environment variables
|
||||
- Get an API Key and Custom Search Engine ID from the previous step, and set them as environment variables
|
||||
`GOOGLE_API_KEY` and `GOOGLE_CSE_ID` respectively.
|
||||
|
||||
```python
|
||||
@ -444,12 +444,12 @@ from langchain_community.utilities.google_trends import GoogleTrendsAPIWrapper
|
||||
|
||||
### Google Document AI
|
||||
|
||||
>[Document AI](https://cloud.google.com/document-ai/docs/overview) is a `Google Cloud Platform`
|
||||
> service that transforms unstructured data from documents into structured data, making it easier
|
||||
>[Document AI](https://cloud.google.com/document-ai/docs/overview) is a `Google Cloud Platform`
|
||||
> service that transforms unstructured data from documents into structured data, making it easier
|
||||
> to understand, analyze, and consume.
|
||||
|
||||
We need to set up a [`GCS` bucket and create your own OCR processor](https://cloud.google.com/document-ai/docs/create-processor)
|
||||
The `GCS_OUTPUT_PATH` should be a path to a folder on GCS (starting with `gs://`)
|
||||
We need to set up a [`GCS` bucket and create your own OCR processor](https://cloud.google.com/document-ai/docs/create-processor)
|
||||
The `GCS_OUTPUT_PATH` should be a path to a folder on GCS (starting with `gs://`)
|
||||
and a processor name should look like `projects/PROJECT_NUMBER/locations/LOCATION/processors/PROCESSOR_ID`.
|
||||
We can get it either programmatically or copy from the `Prediction endpoint` section of the `Processor details`
|
||||
tab in the Google Cloud Console.
|
||||
@ -507,6 +507,23 @@ See a [usage example and authorization instructions](/docs/integrations/toolkits
|
||||
from langchain_community.agent_toolkits import GmailToolkit
|
||||
```
|
||||
|
||||
## Memory
|
||||
|
||||
### Cloud Firestore
|
||||
|
||||
> [`Cloud Firestore`](https://cloud.google.com/firestore) is a NoSQL document database built for automatic scaling, high performance, and ease of application development.
|
||||
|
||||
First, we need to install the python package.
|
||||
|
||||
```bash
|
||||
pip install firebase-admin
|
||||
```
|
||||
|
||||
See a [usage example and authorization instructions](/docs/integrations/memory/firestore_chat_message_history).
|
||||
|
||||
```python
|
||||
from langchain_community.chat_message_histories.firestore import FirestoreChatMessageHistory
|
||||
```
|
||||
|
||||
## Chat Loaders
|
||||
|
||||
@ -560,7 +577,7 @@ from langchain_community.utilities import GoogleSerperAPIWrapper
|
||||
### YouTube
|
||||
|
||||
>[YouTube Search](https://github.com/joetats/youtube_search) package searches `YouTube` videos avoiding using their heavily rate-limited API.
|
||||
>
|
||||
>
|
||||
>It uses the form on the YouTube homepage and scrapes the resulting page.
|
||||
|
||||
We need to install a python package.
|
||||
|
||||
Loading…
Reference in New Issue
Block a user